Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ואין
    -0.08
    紧扣
    -0.08
     มกราคม
    -0.07
     الصف
    -0.07
    海绵
    -0.07
    -transparent
    -0.07
    POCH
    -0.07
    .GetComponent
    -0.07
     совершен
    -0.07
     электро
    -0.06
    POSITIVE LOGITS
    同仁
    0.07
    unj
    0.07
    .rs
    0.07
    #else
    0.07
     outage
    0.07
    (router
    0.07
    ⚗
    0.06
    备份
    0.06
    上诉
    0.06
    	rc
    0.06
    Act Density 0.000%

    No Known Activations